Upload processor (#4)
Browse files- Upload processor (5451064815e2cd3556354241f2f4a45c7c658cf0)
Co-authored-by: Pablo Montalvo <Molbap@users.noreply.huggingface.co>
- preprocessor_config.json +8 -0
- special_tokens_map.json +4 -0
- tokenizer.json +2 -2
- tokenizer_config.json +7 -5
preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_processor_type": "FuyuImageProcessor",
|
3 |
+
"padding_mode": "constant",
|
4 |
+
"padding_value": 1.0,
|
5 |
+
"processor_class": "FuyuProcessor",
|
6 |
+
"target_height": 1080,
|
7 |
+
"target_width": 1920
|
8 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "|ENDOFTEXT|",
|
3 |
"eos_token": "|ENDOFTEXT|",
|
4 |
"unk_token": "<unk>"
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"|ENDOFTEXT|"
|
5 |
+
],
|
6 |
"bos_token": "|ENDOFTEXT|",
|
7 |
"eos_token": "|ENDOFTEXT|",
|
8 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20119416a890c3fefc86210999fb8189dde194c12f7f861dbb3bc7a922baaabb
|
3 |
+
size 16454569
|
tokenizer_config.json
CHANGED
@@ -1,11 +1,9 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
@@ -13,19 +11,23 @@
|
|
13 |
"71013": {
|
14 |
"content": "|ENDOFTEXT|",
|
15 |
"lstrip": false,
|
16 |
-
"normalized":
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
}
|
21 |
},
|
22 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
23 |
"bos_token": "|ENDOFTEXT|",
|
24 |
"clean_up_tokenization_spaces": false,
|
25 |
"eos_token": "|ENDOFTEXT|",
|
26 |
"legacy": true,
|
27 |
"model_max_length": 1000000000000000019884624838656,
|
28 |
"pad_token": null,
|
|
|
29 |
"sp_model_kwargs": {},
|
30 |
"spaces_between_special_tokens": false,
|
31 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
|
|
11 |
"71013": {
|
12 |
"content": "|ENDOFTEXT|",
|
13 |
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
}
|
19 |
},
|
20 |
+
"additional_special_tokens": [
|
21 |
+
"<unk>",
|
22 |
+
"|ENDOFTEXT|"
|
23 |
+
],
|
24 |
"bos_token": "|ENDOFTEXT|",
|
25 |
"clean_up_tokenization_spaces": false,
|
26 |
"eos_token": "|ENDOFTEXT|",
|
27 |
"legacy": true,
|
28 |
"model_max_length": 1000000000000000019884624838656,
|
29 |
"pad_token": null,
|
30 |
+
"processor_class": "FuyuProcessor",
|
31 |
"sp_model_kwargs": {},
|
32 |
"spaces_between_special_tokens": false,
|
33 |
"tokenizer_class": "LlamaTokenizer",
|